Two-year test, NSA or will let its data center wash oiled bath
Source: Internet
Author: User
KeywordsCloud computing data center NSA data center
"Editor's note" Oil cold is not a new thing, as early as two years ago, Green revolution cooling through the oil cold into the eyes of everyone-the company's invention of the carnotjet cooling system compared with air-cooled, only a small energy consumption. It only takes percent of energy to cool down, which is much lower than your traditional server (50%-60%), and the world's most efficient data center, built by Google or Facebook, can drop that number to 10% to 20%, but it's not comparable to an oil-cooled system. Such messages, of course, are not missed by any Big data center player, including the NSA, which began testing green revolution cooling products two years ago.
The following is passage:
Security secret files are likely to be stored in a swimming service in the near future, and the NSA has been exploring the immersion cooling of its huge data center, soaking the servers in a liquid oil-like coolant. The agency says the technology has a huge advantage in reducing cooling costs:
as early as 2012, the NSA's Physical Science laboratory was considering buying and installing an oil-immersed cooling system. We have found that the cost of cooling the server can be greatly reduced by oil immersion cooling. At the same time, this approach could reduce the cost of building half of future data centers.
On the construction of the NSA Utah State Bluffdale's Mega data center, the agency invested 1.5 billion of billions of dollars in the facility, which occupies 1 million flat feet. As a result, this cooling scheme is very attractive, which is why the agency will try Green Revolution cooling (headquartered in Austin) cooling program, but also reflects the NSA's cutting-edge technology to explore the initiative.
Liquid cooling is mainly used in HPC (high performance computing) because its high density configuration is difficult to manage with air cooling. As more applications and services demand higher density configurations, liquid cooling is becoming more and more of a concern, allowing data center players to re-examine the previous infrastructure to overcome the short panels on HPC and the facility.
Advantages of oil Cooling
In contrast to water, mineral oil not only does not conduct electricity, nor does it erode electronic originals, and as a thermal medium, mineral oil can basically be comparable to water. David prucnal, Advanced Computing Bae from the US Department of Defense, said in a quarterly study by the NSA that mineral oil had no specific heat of water and that he could carry 1000 times times as much heat compared to air.
In contrast to air, the greatest advantage of liquid cooling is that it can support higher computational densities. The NSA says that with no other special intervention, the immersion system can support 30-kilowatt per rack, while air cooling can only support 10-15 kw. The immersion cooling eliminates the fan, which is placed on a standard server, and the fan with control air flow consumes approximately 10% of the power of the server.
David also found that immersion cooling, while isolating air pollution, allowed all components of the server to remain at a constant temperature to reduce failure. David added: "Another advantage of immersion cooling is the mute, which, while seemingly innocuous, benefits the health of employees and caters to state regulations." There is, however, a potential obsession with the weight of a server and coolant rack that will reach 3300 pounds, about 1.6 tonnes. ”
Original link: NSA exploring use of Mineral oil to cool its Servers (compiled/Zhonghao revisers/wei)
Free Subscription "CSDN cloud Computing (left) and csdn large data (right)" micro-letter public number, real-time grasp of first-hand cloud news, to understand the latest big data progress!
CSDN publishes related cloud computing information, such as virtualization, Docker, OpenStack, Cloudstack, and data centers, sharing Hadoop, Spark, Nosql/newsql, HBase, Impala, memory calculations, stream computing, Machine learning and intelligent algorithms and other related large data views, providing cloud computing and large data technology, platform, practice and industry information services.
The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion;
products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the
content of the page makes you feel confusing, please write us an email, we will handle the problem
within 5 days after receiving your email.
If you find any instances of plagiarism from the community, please send an email to:
info-contact@alibabacloud.com
and provide relevant evidence. A staff member will contact you within 5 working days.